Faster Optimization-Based Meta-Learning Adaptation Phase
Neural networks require a large amount of annotated data to learn. Meta-learning algorithms propose a way to decrease the number of training samples to only a few. One of the most prominent optimization-based meta-learning algorithms is Model-Agnostic Meta-Learning (MAML). However, the key procedure of adaptation to new tasks in MAML is quite slow. In this work we propose an improvement to MAML meta-learning algorithm. We introduce Lambda patterns by which we restrict which weight are updated in the network during the adaptation phase. This makes it possible to skip certain gradient computations. The fastest pattern is selected given an allowed quality degradation threshold parameter. In certain cases, quality improvement is possible by a careful pattern selection. The experiments conducted have shown that via Lambda adaptation pattern selection, it is possible to significantly improve the MAML method in the following areas: adaptation time has been decreased by a factor of 3 with minimal accuracy loss; accuracy for one-step adaptation has been substantially improved.
Code (0)
등록된 구현이 없습니다.
Tasks
Meta-LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Geometry Aware Meta-Learning Neural Network for Joint Phase and Precoder Optimization in RIS
In reconfigurable intelligent surface (RIS) aided systems, the joint optimization of the precoder matrix at the base station and the phase shifts of the RIS elements involves significant complexity. In this paper, we pro…
Meta-LearningBridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptation
Multi-task learning (MTL) aims to improve the generalization of several related tasks by learning them jointly. As a comparison, in addition to the joint training scheme, modern meta-learning allows unseen tasks with lim…
Few-Shot Image Classificationimage-classificationImage ClassificationMeta-Learning+1Learning Fast Adaptation with Meta Strategy Optimization
The ability to walk in new scenarios is a key milestone on the path toward real-world applications of legged robots. In this work, we introduce Meta Strategy Optimization, a meta-learning algorithm for training policies …
Meta-LearningConstrained Meta Agnostic Reinforcement Learning
Meta-Reinforcement Learning (Meta-RL) aims to acquire meta-knowledge for quick adaptation to diverse tasks. However, applying these policies in real-world environments presents a significant challenge in balancing rapid …
Meta-LearningMeta Reinforcement Learningreinforcement-learningReinforcement LearningGeM-EA: A Generative and Meta-learning Enhanced Evolutionary Algorithm for Streaming Data-Driven Optimization
Streaming Data-Driven Optimization (SDDO) problems arise in many applications where data arrive continuously and the optimization environment evolves over time. Concept drift produces non-stationary landscapes, making op…